Abstract
Typical feature pools used to train boosted object detectors contain various redundant and unspecific information which often yield less discriminative detectors. In this paper we introduce a feature mining algorithm taking domain specific knowledge into account. Our proposed feature pool contains rectangular shaped features generated from an image clustering algorithm applied on the mean image of the object training set. A combination of two such spatially separated rectangular regions yields a set of features which have a similar evaluation time like classical Haar-like features, but are much smarter (automatically) selected and more discriminative since image correlations can be more consequently exploited. Overall, training is faster and results in more selective detectors showing improved precision. Several experiments demonstrate the gain when using our proposed feature set in contrast to standard features.
Chapter PDF
Similar content being viewed by others
References
Viola, P., Jones, M.J.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)
Dollár, P., Tu, Z., Tao, H., Belongie, S.: Feature mining for image classification. In: CVPR. IEEE Computer Society (2007)
Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. In: Artificial Intelligence, vol. 97, pp. 245–271 (1997)
Koller, D., Sahami, M.: Toward optimal feature selection. In: ICML, pp. 284–292. Morgan Kaufmann (1996)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Zhao, X., Chai, X., Niu, Z., Heng, C., Shan, S.: Context constrained facial landmark localization based on discontinuous haar-like feature. In: FG, pp. 673–678. IEEE (2011)
Sung, K.K., Poggio, T., Rowley, H.A., Baluja, S., Kanade, T.: MIT+CMU frontal face dataset a, b and c. MIT+CMU (1998)
Jain, V., Learned-Miller, E.: Fddb: A benchmark for face detection in unconstrained settings. Technical Report UM-CS-2010-009, University of Massachusetts, Amherst (2010)
Agarwal, S., Awan, A., Roth, D.: UIUC image database for car detection (2002)
Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. IEEE ICIP 2002 (2002)
Stanciulescu, B., Breheret, A., Moutarde, F.: Introducing new adaboost features for real-time vehicle detection. In: COGIS (2007)
Moutarde, F., Stanciulescu, B., Breheret, A.: Real-time visual detection of vehicles and pedestrians with new efficient adaboost features. In: IEEE IROS (2008)
Pham, M.T., Gao, Y., Hoang, V.D.D., Cham, T.J.: Fast polygonal integration and its application in extending haar-like features to improve object detection. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) (2010)
Smith, K., Carleton, A., Lepetit, V.: Fast ray features for learning irregular shapes. In: IEEE: ICCV, pp. 397–404 (2009)
Hartigan, J.A., Wong, M.A.: Algorithm as 136: A k-means clustering algorithm. Journal of the Royal Statistical Society 28(1), 100–108 (1979)
Meyer, F.: Topographic distance and watershed lines. In: Signal Processing, vol. 38, pp. 113–125 (1994)
Ren, X., Malik, J.: Learning a classification model for segmentation. In: 9th Int. Conf. Computer Vision, vol. 1, pp. 10–17 (2003)
Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: Combining segmentation and recognition. In: IEEE Computer Vision and Pattern Recognition (2004)
Lantuéjoul, C.: La squelettisation et son application aux mesures topologiques des mosaiques poly- cristallines. PhD thesis, Ecole des Mines (1978)
Digabel, H., Lantuéjoul, C.: Iterative algorithms. In: Actes du Second Symposium Européen d’Analyse Quantitative des Microstructures en Sciences des Matériaux, pp. 85–99 (1977)
Schapire, R.E., Freund, Y., Bartlett, P., Lee, W.S.: Boosting the margin: A new explanation for the effectiveness of voting methods. In: Proceedings of the Fourteenth International Conference on Machine Learning (ICML), pp. 322–330 (1997)
The MPLab GENKI Database, u.S.: http://mplab.ucsd.edu . - (-)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)
Li, J., Wang, T., Zhang, Y.: Face detection using surf cascade. In: ICCV Workshops, pp. 2183–2190. IEEE (2011)
Jain, V., Learned-Miller, E.G.: Online domain adaptation of a pre-trained cascade of classifiers. In: CVPR, pp. 577–584. IEEE (2011)
Mikolajczyk, K., Schmid, C., Zisserman, A.: Human detection based on a probabilistic assembly of robust part detectors. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 69–82. Springer, Heidelberg (2004)
Subburaman, V.B., Marcel, S.: Fast Bounding Box Estimation based Face Detection. In: ECCV, Workshop on Face Detection: Where We Are, and What Next? (2010)
Bradski, G.: The opencv library. Dr. Dobb’s Journal of Software Tools (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ehlers, A., Baumann, F., Rosenhahn, B. (2013). Exploiting Object Characteristics Using Custom Features for Boosting-Based Classification. In: Kämäräinen, JK., Koskela, M. (eds) Image Analysis. SCIA 2013. Lecture Notes in Computer Science, vol 7944. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38886-6_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-38886-6_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38885-9
Online ISBN: 978-3-642-38886-6
eBook Packages: Computer ScienceComputer Science (R0)